SBIR Phase I: Resilience for Waterfront Infrastructure (“REWIRE”)

SBIR一期项目的更广泛影响/商业潜力是支持面临侵蚀、海平面上升和沿海风暴风险的可持续沿海社区和基础设施。世界上大约50%的人口居住在离海岸50英里的范围内，向沿海地区迁移的人口正在增加。这些地区面临的风险反映在保险和联邦应急管理局索赔的大幅增加上。该项目将研究和开发软件系统，简化基于自然的海岸保护解决方案的分析、许可和实施，这些解决方案已被证明能够适应这些风险并提供环境效益。该项目将开发跨领域技术，增强我们对沿海科学和工程的了解，并利用基于自然的方法来解决沿海完整性问题，与传统的人工数据收集、分析和工程方法相比，将带来更大的生态、成本和性能优势。增强沿海社区的抵御能力、加强渔业和适应性基础设施解决方案将激励私营部门在这些地区的投资。SBIR第一期项目建议开发一个集成软件系统，通过自动化表征近岸植被指示物种与海岸线保护行动的关系，制定智能海岸维护解决方案。人们普遍认为，岸线稳定性与近岸植物健康有关，但分析和解释具有足够确定性水平的复杂数据集难以规定具体的维护行动，因此有必要调查和制定新的分析框架。主要技术目标是开发一种机器学习和贝叶斯推理决策支持工具，该工具结合了来自现有图像数据库、多光谱无人机图像、RTK测深和海岸线维护行动的数据，用于实验验证。这种方法将适用于各种植被侵蚀的海岸线系统（即湿地、海岸沙丘和红树林）。预期的结果是一个商业系统的技术基础，以更低的成本更有效地管理沿海基础设施风险，并为社会带来更大的生态效益。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/ commercial potential of this SBIR Phase I project is to support sustainable coastal communities and infrastructure facing risks due to erosion, sea level rise, and coastal storms. Approximately 50% of the world’s population lives within 50 miles of the coast and migration toward coastal areas is increasing. The risks to these areas are reflected in the substantial increase in insurance and FEMA claims. This project will research and develop software systems that streamline the analysis, permitting, and implementation of nature-based coastal protection solutions that have been proven to adapt to these risks and provide environmental benefits. This project will develop cross-cutting technologies that will enhance our knowledge of coastal sciences and engineering and leverage nature-based approaches to coastal integrity issues, leading to increasing ecological, cost, and performance advantages compared to traditional manual methods of data collection, analysis and engineering. The empowerment of more resilient coastal communities, enhanced fisheries, and adaptive infrastructure solutions will incentivize private sector investment in these regions. This SBIR Phase I project proposes to develop an integrated software system to prescribe intelligent coastal maintenance solutions through the automated characterization of the relationship of near-shore vegetative indicator species with shoreline protective actions. It is generally understood that shoreline stability is related to nearshore vegetative health, but the difficulty of analyzing and interpreting the complex data sets with certainty levels sufficient to prescribe specific maintenance actions necessitates the investigation and development of a new analytical framework. The principal technical objective is the development of a machine learning and bayesian inference decision support tool incorporating data from existing imagery databases, multispectral UAV imagery, RTK bathymetry, and shoreline maintenance actions for experimental validation. This approach would be applicable to a wide variety of vegetated erosional shoreline systems (i.e. wetlands, coastal dunes, and mangroves). The anticipated result is the technical foundation of a commercial system to more efficiently manage coastal infrastructure risk at lower costs and with enhanced ecological benefits for society.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.